© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203774
    Prev
    Next
    INDEX
    Explanations

    mathematical subscripts and superscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ت
    1.41
    ↵
    1.18
     was
    1.17
    y
    1.16
    4
    1.09
     is
    1.07
    5
    1.07
    ac
    1.00
     on
    1.00
    b
    1.00
    POSITIVE LOGITS
    ти
    1.27
    𝟘
    1.20
    ill
    1.10
    Flicky
    1.09
    TARGETTING
    1.04
     말미암
    0.97
    ⓪
    0.95
     Tattha
    0.95
    他に
    0.95
    >∞</
    0.95
    Activations Density 0.000%

    No Known Activations